Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1153 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4945. Min Act: -0.1700
Data Index: 6944525 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4320. Min Act: -0.1700
Data Index: 2149479 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4320. Min Act: -0.1700
Data Index: 6460810 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4007. Min Act: -0.1700
Data Index: 2998195 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4320. Min Act: -0.1700
Data Index: 8540019 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4007. Min Act: -0.1700
Data Index: 2885333 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3382. Min Act: -0.1700
Data Index: 608187 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3382. Min Act: -0.1700
Data Index: 2161070 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3070. Min Act: -0.1700
Data Index: 908908 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3070. Min Act: -0.1700
Data Index: 7701808 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3070. Min Act: -0.1700
Data Index: 8156845 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 3485875 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 1561677 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3070. Min Act: -0.1700
Data Index: 4624498 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 7200036 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2445. Min Act: -0.1700
Data Index: 798060 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2445. Min Act: -0.1700
Data Index: 177108 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2445. Min Act: -0.1700
Data Index: 305083 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2132. Min Act: -0.1700
Data Index: 1180551 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2132. Min Act: -0.1700
Data Index: 5106767 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19